8 files changed, 161 insertions, 37 deletions

diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index cbc1184e9473..1b452a1665c4 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -9,6 +9,7 @@ obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o \
                 pci-dma.o i386_ksyms.o i387.o bootflag.o \
                 quirks.o i8237.o topology.o alternative.o i8253.o tsc.o
 
+obj-$(CONFIG_STACKTRACE)        += stacktrace.o
 obj-y                           += cpu/
 obj-y                           += acpi/
 obj-$(CONFIG_X86_BIOS_REBOOT)   += reboot.o
diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
index 7b421b3a053e..28ab80649764 100644
--- a/arch/i386/kernel/alternative.c
+++ b/arch/i386/kernel/alternative.c
@@ -303,6 +303,16 @@ void alternatives_smp_switch(int smp)
         struct smp_alt_module *mod;
         unsigned long flags;
 
+#ifdef CONFIG_LOCKDEP
+        /*
+         * A not yet fixed binutils section handling bug prevents
+         * alternatives-replacement from working reliably, so turn
+         * it off:
+         */
+        printk("lockdep: not fixing up alternatives.\n");
+        return;
+#endif
+
         if (no_replacement || smp_alt_once)
                 return;
         BUG_ON(!smp && (num_online_cpus() > 1));
diff --git a/arch/i386/kernel/cpuid.c b/arch/i386/kernel/cpuid.c
index a8d3ecdc3897..fde8bea85cee 100644
--- a/arch/i386/kernel/cpuid.c
+++ b/arch/i386/kernel/cpuid.c
@@ -167,6 +167,7 @@ static int cpuid_class_device_create(int i)
         return err;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 static int cpuid_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
@@ -186,6 +187,7 @@ static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier =
 {
         .notifier_call = cpuid_class_cpu_callback,
 };
+#endif /* !CONFIG_HOTPLUG_CPU */
 
 static int __init cpuid_init(void)
 {
@@ -208,7 +210,7 @@ static int __init cpuid_init(void)
                 if (err != 0) 
                         goto out_class;
         }
-        register_cpu_notifier(&cpuid_class_cpu_notifier);
+        register_hotcpu_notifier(&cpuid_class_cpu_notifier);
 
         err = 0;
         goto out;
@@ -233,7 +235,7 @@ static void __exit cpuid_exit(void)
                 class_device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu));
         class_destroy(cpuid_class);
         unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");
-        unregister_cpu_notifier(&cpuid_class_cpu_notifier);
+        unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
 }
 
 module_init(cpuid_init);
diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 787190c45fdb..d9a260f2efb4 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -42,6 +42,7 @@
 
 #include <linux/linkage.h>
 #include <asm/thread_info.h>
+#include <asm/irqflags.h>
 #include <asm/errno.h>
 #include <asm/segment.h>
 #include <asm/smp.h>
@@ -76,12 +77,21 @@ NT_MASK		= 0x00004000
 VM_MASK         = 0x00020000
 
 #ifdef CONFIG_PREEMPT
-#define preempt_stop            cli
+#define preempt_stop            cli; TRACE_IRQS_OFF
 #else
 #define preempt_stop
 #define resume_kernel           restore_nocheck
 #endif
 
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+        testl $IF_MASK,EFLAGS(%esp)     # interrupts off?
+        jz 1f
+        TRACE_IRQS_ON
+1:
+#endif
+.endm
+
 #ifdef CONFIG_VM86
 #define resume_userspace_sig    check_userspace
 #else
@@ -257,6 +267,10 @@ ENTRY(sysenter_entry)
         CFI_REGISTER esp, ebp
         movl TSS_sysenter_esp0(%esp),%esp
 sysenter_past_esp:
+        /*
+         * No need to follow this irqs on/off section: the syscall
+         * disabled irqs and here we enable it straight after entry:
+         */
         sti
         pushl $(__USER_DS)
         CFI_ADJUST_CFA_OFFSET 4
@@ -303,6 +317,7 @@ sysenter_past_esp:
         call *sys_call_table(,%eax,4)
         movl %eax,EAX(%esp)
         cli
+        TRACE_IRQS_OFF
         movl TI_flags(%ebp), %ecx
         testw $_TIF_ALLWORK_MASK, %cx
         jne syscall_exit_work
@@ -310,6 +325,7 @@ sysenter_past_esp:
         movl EIP(%esp), %edx
         movl OLDESP(%esp), %ecx
         xorl %ebp,%ebp
+        TRACE_IRQS_ON
         sti
         sysexit
         CFI_ENDPROC
@@ -339,6 +355,7 @@ syscall_exit:
         cli                             # make sure we don't miss an interrupt
                                         # setting need_resched or sigpending
                                         # between sampling and the iret
+        TRACE_IRQS_OFF
         movl TI_flags(%ebp), %ecx
         testw $_TIF_ALLWORK_MASK, %cx   # current->work
         jne syscall_exit_work
@@ -355,12 +372,15 @@ restore_all:
         CFI_REMEMBER_STATE
         je ldt_ss                       # returning to user-space with LDT SS
 restore_nocheck:
+        TRACE_IRQS_IRET
+restore_nocheck_notrace:
         RESTORE_REGS
         addl $4, %esp
         CFI_ADJUST_CFA_OFFSET -4
 1:      iret
 .section .fixup,"ax"
 iret_exc:
+        TRACE_IRQS_ON
         sti
         pushl $0                        # no error code
         pushl $do_iret_error
@@ -386,11 +406,13 @@ ldt_ss:
         subl $8, %esp           # reserve space for switch16 pointer
         CFI_ADJUST_CFA_OFFSET 8
         cli
+        TRACE_IRQS_OFF
         movl %esp, %eax
         /* Set up the 16bit stack frame with switch32 pointer on top,
          * and a switch16 pointer on top of the current frame. */
         call setup_x86_bogus_stack
         CFI_ADJUST_CFA_OFFSET -8        # frame has moved
+        TRACE_IRQS_IRET
         RESTORE_REGS
         lss 20+4(%esp), %esp    # switch to 16bit stack
 1:      iret
@@ -411,6 +433,7 @@ work_resched:
         cli                             # make sure we don't miss an interrupt
                                         # setting need_resched or sigpending
                                         # between sampling and the iret
+        TRACE_IRQS_OFF
         movl TI_flags(%ebp), %ecx
         andl $_TIF_WORK_MASK, %ecx      # is there any work to be done other
                                         # than syscall tracing?
@@ -462,6 +485,7 @@ syscall_trace_entry:
 syscall_exit_work:
         testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl
         jz work_pending
+        TRACE_IRQS_ON
         sti                             # could let do_syscall_trace() call
                                         # schedule() instead
         movl %esp, %eax
@@ -535,9 +559,14 @@ ENTRY(irq_entries_start)
 vector=vector+1
 .endr
 
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
         ALIGN
 common_interrupt:
         SAVE_ALL
+        TRACE_IRQS_OFF
         movl %esp,%eax
         call do_IRQ
         jmp ret_from_intr
@@ -549,9 +578,10 @@ ENTRY(name)				\
         pushl $~(nr);                   \
         CFI_ADJUST_CFA_OFFSET 4;        \
         SAVE_ALL;                       \
+        TRACE_IRQS_OFF                  \
         movl %esp,%eax;                 \
         call smp_/**/name;              \
-        jmp ret_from_intr;      \
+        jmp ret_from_intr;              \
         CFI_ENDPROC
 
 /* The include is where all of the SMP etc. interrupts come from */
@@ -726,7 +756,7 @@ nmi_stack_correct:
         xorl %edx,%edx          # zero error code
         movl %esp,%eax          # pt_regs pointer
         call do_nmi
-        jmp restore_all
+        jmp restore_nocheck_notrace
         CFI_ENDPROC
 
 nmi_stack_fixup:
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index 16b491703967..6cb529f60dcc 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -166,7 +166,7 @@ void irq_ctx_init(int cpu)
         irqctx->tinfo.task              = NULL;
         irqctx->tinfo.exec_domain       = NULL;
         irqctx->tinfo.cpu               = cpu;
-        irqctx->tinfo.preempt_count     = SOFTIRQ_OFFSET;
+        irqctx->tinfo.preempt_count     = 0;
         irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
 
         softirq_ctx[cpu] = irqctx;
@@ -211,6 +211,10 @@ asmlinkage void do_softirq(void)
                         : "0"(isp)
                         : "memory", "cc", "edx", "ecx", "eax"
                 );
+                /*
+                 * Shouldnt happen, we returned above if in_interrupt():
+                 */
+                WARN_ON_ONCE(softirq_count());
         }
 
         local_irq_restore(flags);
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index a76e93146585..2dd928a84645 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -107,7 +107,7 @@ int nmi_active;
 static __init void nmi_cpu_busy(void *data)
 {
         volatile int *endflag = data;
-        local_irq_enable();
+        local_irq_enable_in_hardirq();
         /* Intentionally don't use cpu_relax here. This is
            to make sure that the performance counter really ticks,
            even if there is a simulator or similar that catches the
diff --git a/arch/i386/kernel/stacktrace.c b/arch/i386/kernel/stacktrace.c
new file mode 100644
index 000000000000..e62a037ab399
--- /dev/null
+++ b/arch/i386/kernel/stacktrace.c
@@ -0,0 +1,98 @@
+/*
+ * arch/i386/kernel/stacktrace.c
+ *
+ * Stack trace management functions
+ *
+ *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+
+static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
+{
+        return  p > (void *)tinfo &&
+                p < (void *)tinfo + THREAD_SIZE - 3;
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer:
+ */
+static inline unsigned long
+save_context_stack(struct stack_trace *trace, unsigned int skip,
+                   struct thread_info *tinfo, unsigned long *stack,
+                   unsigned long ebp)
+{
+        unsigned long addr;
+
+#ifdef CONFIG_FRAME_POINTER
+        while (valid_stack_ptr(tinfo, (void *)ebp)) {
+                addr = *(unsigned long *)(ebp + 4);
+                if (!skip)
+                        trace->entries[trace->nr_entries++] = addr;
+                else
+                        skip--;
+                if (trace->nr_entries >= trace->max_entries)
+                        break;
+                /*
+                 * break out of recursive entries (such as
+                 * end_of_stack_stop_unwind_function):
+                 */
+                if (ebp == *(unsigned long *)ebp)
+                        break;
+
+                ebp = *(unsigned long *)ebp;
+        }
+#else
+        while (valid_stack_ptr(tinfo, stack)) {
+                addr = *stack++;
+                if (__kernel_text_address(addr)) {
+                        if (!skip)
+                                trace->entries[trace->nr_entries++] = addr;
+                        else
+                                skip--;
+                        if (trace->nr_entries >= trace->max_entries)
+                                break;
+                }
+        }
+#endif
+
+        return ebp;
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ * If all_contexts is set, all contexts (hardirq, softirq and process)
+ * are saved. If not set then only the current context is saved.
+ */
+void save_stack_trace(struct stack_trace *trace,
+                      struct task_struct *task, int all_contexts,
+                      unsigned int skip)
+{
+        unsigned long ebp;
+        unsigned long *stack = &ebp;
+
+        WARN_ON(trace->nr_entries || !trace->max_entries);
+
+        if (!task || task == current) {
+                /* Grab ebp right from our regs: */
+                asm ("movl %%ebp, %0" : "=r" (ebp));
+        } else {
+                /* ebp is the last reg pushed by switch_to(): */
+                ebp = *(unsigned long *) task->thread.esp;
+        }
+
+        while (1) {
+                struct thread_info *context = (struct thread_info *)
+                                ((unsigned long)stack & (~(THREAD_SIZE - 1)));
+
+                ebp = save_context_stack(trace, skip, context, stack, ebp);
+                stack = (unsigned long *)context->previous_esp;
+                if (!all_contexts || !stack ||
+                                trace->nr_entries >= trace->max_entries)
+                        break;
+                trace->entries[trace->nr_entries++] = ULONG_MAX;
+                if (trace->nr_entries >= trace->max_entries)
+                        break;
+        }
+}
+
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index e8c6086b2aa1..2bf8b55b91f8 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -115,28 +115,13 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
 }
 
 /*
- * Print CONFIG_STACK_BACKTRACE_COLS address/symbol entries per line.
+ * Print one address/symbol entries per line.
  */
-static inline int print_addr_and_symbol(unsigned long addr, char *log_lvl,
-                                        int printed)
+static inline void print_addr_and_symbol(unsigned long addr, char *log_lvl)
 {
-        if (!printed)
-                printk(log_lvl);
-
-#if CONFIG_STACK_BACKTRACE_COLS == 1
         printk(" [<%08lx>] ", addr);
-#else
-        printk(" <%08lx> ", addr);
-#endif
-        print_symbol("%s", addr);
 
-        printed = (printed + 1) % CONFIG_STACK_BACKTRACE_COLS;
-        if (printed)
-                printk(" ");
-        else
-                printk("\n");
-
-        return printed;
+        print_symbol("%s\n", addr);
 }
 
 static inline unsigned long print_context_stack(struct thread_info *tinfo,
@@ -144,12 +129,11 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
                                 char *log_lvl)
 {
         unsigned long addr;
-        int printed = 0; /* nr of entries already printed on current line */
 
 #ifdef  CONFIG_FRAME_POINTER
         while (valid_stack_ptr(tinfo, (void *)ebp)) {
                 addr = *(unsigned long *)(ebp + 4);
-                printed = print_addr_and_symbol(addr, log_lvl, printed);
+                print_addr_and_symbol(addr, log_lvl);
                 /*
                  * break out of recursive entries (such as
                  * end_of_stack_stop_unwind_function):
@@ -162,28 +146,23 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
         while (valid_stack_ptr(tinfo, stack)) {
                 addr = *stack++;
                 if (__kernel_text_address(addr))
-                        printed = print_addr_and_symbol(addr, log_lvl, printed);
+                        print_addr_and_symbol(addr, log_lvl);
         }
 #endif
-        if (printed)
-                printk("\n");
-
         return ebp;
 }
 
-static asmlinkage int show_trace_unwind(struct unwind_frame_info *info, void *log_lvl)
+static asmlinkage int
+show_trace_unwind(struct unwind_frame_info *info, void *log_lvl)
 {
         int n = 0;
-        int printed = 0; /* nr of entries already printed on current line */
 
         while (unwind(info) == 0 && UNW_PC(info)) {
-                ++n;
-                printed = print_addr_and_symbol(UNW_PC(info), log_lvl, printed);
+                n++;
+                print_addr_and_symbol(UNW_PC(info), log_lvl);
                 if (arch_unw_user_mode(info))
                         break;
         }
-        if (printed)
-                printk("\n");
         return n;
 }